Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.1917. Min Act: -0.1700
Data Index: 5751709 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.1917. Min Act: -0.1700
Data Index: 8769115 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.1604. Min Act: -0.1700
Data Index: 7886188 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0979. Min Act: -0.1700
Data Index: 3700327 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0354. Min Act: -0.1700
Data Index: 4389070 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0667. Min Act: -0.1700
Data Index: 3634802 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0354. Min Act: -0.1700
Data Index: 728443 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0354. Min Act: -0.1700
Data Index: 6923748 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0354. Min Act: -0.1700
Data Index: 7156813 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0354. Min Act: -0.1700
Data Index: 3919230 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0042. Min Act: -0.1700
Data Index: 8391912 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0042. Min Act: -0.1700
Data Index: 7219725 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1917. Min Range: -5.1917
Max Act: 5.0354. Min Act: -0.1700
Data Index: 6824871 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2715321 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.9417. Min Act: -0.1700
Data Index: 1828109 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.9104. Min Act: -0.1700
Data Index: 6935140 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.9104. Min Act: -0.1700
Data Index: 969342 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.9104. Min Act: -0.1700
Data Index: 3349622 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.9104. Min Act: -0.1700
Data Index: 2426344 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1917. Min Range: -5.1917
Max Act: 4.8792. Min Act: -0.1700
Data Index: 4538103 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19